[itsdb] parse big corpus with itsdb
Francis Bond
fcbond at gmail.com
Wed Nov 8 02:36:45 CET 2006
G'day,
shouldn't you be asleep by now?
> I am wondering what exactly is the difference between -results --- I know
> what that one is --- and -nsolutions. Can anyone enlighten me here?
I think:
-results sits in the output routine and stops it printing all the
results. They are still all calculated.
-nsolutions asks cheap to only produce the top "n" parses.
- with no model, I don't knwo what it does
- with just a scoring model it uses some kind of beam search (I think)
-- this means that the result is often not the global optimum
- with selective unpacking it should produce the global best n results
-- without having to explore the whole search space
Stephen, Bernd or Yi, please correct me if I am wrong.
--
Francis Bond <www.kecl.ntt.co.jp/icl/mtg/members/bond/>
NTT Communication Science Laboratories | Natural Language Research Group
More information about the itsdb
mailing list